• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.877-884
• /
• 2011

The decision tree is a representative algorithm of data mining and used in many domains such as retail target marketing, fraud detection, data reduction, variable screening, category merging, etc. This method is most useful in classification problems, and to make predictions for a target group after dividing it into several small groups. When we create a model of decision tree with a large number of input variables, we suffer difficulties in exploration and analysis of the model because of complex trees. And we can often find some association exist between input variables by external variables despite of no intrinsic association. In this paper, we study on the removal method of unnecessary input variables using multiple external association rules. And then we apply the removal method to actual data for its efficiencies.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.594-600
• /
• 2017

The new design methodology of prediction model and pattern classification, which is based on the dimension reduction algorithm called principal component analysis, is introduced in this paper. Principal component analysis is one of dimension reduction techniques which are used to reduce the dimension of the input space and extract some good features from the original input variables. The extracted input variables are applied to the prediction model and pattern classifier as the input variables. The introduced prediction model and pattern classifier are based on the very simple regression which is the key point of the paper. The structural simplicity of the prediction model and pattern classifier leads to reducing the over-fitting problem. In order to validate the proposed prediction model and pattern classifier, several machine learning data sets are used.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2019

The proposed model is developed to minimize the loss of information in incomplete data including missing data. The first step is to transform the learning data to compensate for the loss information using the data extension technique. In this conversion process, the attribute values of the data are filled with binary or probability values in one-hot encoding. Next, this conversion data is input to the deep learning model, where the number of entries is not constant depending on the cardinality of each attribute. Then, the entry values of each attribute are assigned to the respective input nodes, and learning proceeds. This is different from existing learning models, and has an unusual structure in which arbitrary attribute values are distributedly input to multiple nodes in the input layer. In order to evaluate the learning performance of the proposed model, various experiments are performed on the missing data and it shows that it is superior in terms of performance. The proposed model will be useful as an algorithm to minimize the loss in the ubiquitous environment.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.13 no.3
• /
• pp.288-300
• /
• 2002

In this paper, a novel method of equalization of RF transceivers is suggested for MIMO(Multiple Input Multiple Output) antenna actively studied for high speed data transmission in the recent IMT-2000 system. The core of suggestion is in equalizing the transfer characteristics of multiple transceivers using feedback and memory during the predefined calibration time. This makes it possible to weight the signals in the intermediate frequency, which is easier in the application of recently developed DoA(Direction of Arrival) algorithms. In addition, the time varying optimum cell formation according to traffic is feasible by antenna beam-forming based on the DoA information. The suggested method of equalizing multiple transceivers are successfully verified using envelope simulation. two outputs. This paper is concerned with the diagnosis of multiple crosstalk-faults in OSM. As the network size becomes larger in these days, the convent.
nal diagnosis methods based on tests and simulation be.
me inefficient, or even more impractical. We propose a simple and easily implementable alg？ithm for detection and isolation of the multiple crosstalk-faults in OSM. Specifically, we develop an algorithm for isolation of the source fault in switc.
ng elements whenever the multiple crosstalk-faults are.
etected in OSM. The proposed algorithm is illustrated by an example of 16$\times$16 OSM.

• Journal of the Korea Society for Simulation
• /
• v.20 no.3
• /
• pp.19-28
• /
• 2011

Adaptive Random Testing (ART) aims to enhance the performance of pure random testing by detecting failure region in a software. The ART algorithm generates effective test cases which requires less number of test cases than that of pure random testing. However, all ART algorithms currently proposed are designed for the tests of monolithic system or unit level. In case of integrated system tests, ART approaches do not achieve same performances as those of ARTs applied to the unit or monolithic system. In this paper, we propose an extended ART algorithm which can be applied to the integrated system testing environment without degradation of performance. The proposed approach investigates an input distribution of the unit under a test with limited number of seed input data and generates information to be used to resizing input domain partitions. The simulation results show that our approach in an integration environment could achieve similar level of performance as an ART is applied to a unit testing. Results also show resilient effectiveness for various failure rates.

• Journal of Communications and Networks
• /
• v.18 no.3
• /
• pp.273-287
• /
• 2016

White-box cryptography presented by Chow et al. is an obfuscation technique for protecting secret keys in software implementations even if an adversary has full access to the implementation of the encryption algorithm and full control over its execution platforms. Despite its practical importance, progress has not been substantial. In fact, it is repeated that as a proposal for a white-box implementation is reported, an attack of lower complexity is soon announced. This is mainly because most cryptanalytic methods target specific implementations, and there is no general attack tool for white-box cryptography. In this paper, we present an analytic toolbox on white-box implementations of the Chow et al.'s style using lookup tables. According to our toolbox, for a substitution-linear transformation cipher on n bits with S-boxes on m bits, the complexity for recovering the $$O\((3n/max(m_Q,m))2^{3max(m_Q,m)}+2min\{(n/m)L^{m+3}2^{2m},\;(n/m)L^32^{3m}+n{\log}L{\cdot}2^{L/2}\}\)$$, where $m_Q$ is the input size of nonlinear encodings,$m_A$ is the minimized block size of linear encodings, and $L=lcm(m_A,m_Q)$. As a result, a white-box implementation in the Chow et al.'s framework has complexity at most $O\(min\{(2^{2m}/m)n^{m+4},\;n{\log}n{\cdot}2^{n/2}\}\)$ which is much less than $2^n$. To overcome this, we introduce an idea that obfuscates two advanced encryption standard (AES)-128 ciphers at once with input/output encoding on 256 bits. To reduce storage, we use a sparse unsplit input encoding. As a result, our white-box AES implementation has up to 110-bit security against our toolbox, close to that of the original cipher. More generally, we may consider a white-box implementation of the t parallel encryption of AES to increase security.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.983-989
• /
• 2006

Current emigration and immigration control inspects passports by the naked eye, registers them by manual input, and compares them with items of database. In this paper, we propose the method to recognize information codes of passports. The proposed passport recognition method extracts character-rows of information codes by applying sobel operator, horizontal smearing, and contour tracking algorithm. The extracted letter-row regions is binarized. After a CDM mask is applied to them in order to recover the individual codes, the individual codes are extracted by applying vertical smearing. The recognizing of individual codes is performed by the RBF network whose hidden layer is applied by ART 2 algorithm and whose learning between the hidden layer and the output layer is applied by a generalized delta learning method. After a photo region is extracted from the reference of the starting point of the extracted character-rows of information codes, that region is verified by the information of luminance, edge, and hue. The verified photo region is certified by the classified features by the ART 2 algorithm. The comparing experiment with real passport images confirmed the good performance of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.9A
• /
• pp.1290-1298
• /
• 2000

Turbo Code decoder is an iterate decoding technology, which extracts extrinsic information from the bit to be decoded by calculating both forward and backward metrics, and uses the information to the next decoding step Turbo Code shows excellent performance, approaching Shannon Limit at the view of BER, when the size of Interleaver is big and iterate decoding is run enough. But it has the problems which are increased complexity and delay and difficulty of real-time processing due to Interleaver and iterate decoding. In this paper, it is analyzed that MAP(maximum a posteriori) algorithm which is used as one of Turbo Code decoding, and the factor which determines its performance. MAP algorithm proceeds iterate decoding by determining soft decision value through the environment and transition probability between all adjacent bits and received symbols. Therefore, to improve the performance of MAP algorithm, the trust between adjacent received symbols must be ensured. However, MAP algorithm itself, can not do any action for ensuring so the conclusion is that it is needed more algorithm, so to decrease iterate decoding. Consequently, MAP algorithm and Turbo Code performance are analyzed in the nongaussian channel applying Robust equalization technique in order to input more trusted information into MAP algorithm for the received symbols.

• Annual Conference of KIPS
• /
• 2006.05a
• /
• pp.325-328
• /
• 2006

역전파 학습 방법은 속도가 느리고, 지역 최소점으로 빠져 수렴에 실패하는 경우가 많다고 알려져 있다. 이제까지 알려진 역전파의 대체 방법들은 수렴 속도와 인자에 따른 수렴의 안정성에 대한 불균형을 해소 하는데 치중했다. 기존의 전통적인 역전파에서 발생하는 위와 같은 문제를 해결하기 위하여, 본 논문에서는 적은 용량의 저장 공간만을 요구하며 수렴이 빠르고 상대적으로 안정성이 보장되는 알고리즘을 제안한다. 이 방법은 상위연결(upper connections), 은닉층-출력층(hidden to output), 하위 연결(lower connections), 입력층-은닉층(input to hidden)에 대해 개별적으로 훈련을 시키는 교대 학습 방법을 적용한다.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.339-340
• /
• 2006

In this paper, a low-power deblocking filter structure for H.264 video coding algorithm is proposed. By sharing addition hardware for common filter coefficients, we have designed an efficient deblocking filter structure. Proposed deblocking filter utilizes MUX and DEMUX circuits for input data sharing and shows 44.2% reduction for add operation. In the HDL coding simulation and FPGA implementation, we achieved 19.5% and 19.4% gate count reduction, respectively, comparison with the conventional deblocking filter structure.